Unmanned aerial vehicle abnormal behavior recognition method based on convolutional neural network

An identification method and technology for drones, applied in the field of drones, can solve problems such as inability to detect and meet various requirements for abnormal behavior, and achieve the effect of reducing the degree of human intervention and improving the recognition accuracy.

Inactive Publication Date: 2019-12-31
北航(四川)西部国际创新港科技有限公司
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the drone itself is flying normally, this part cannot be detected
Can not meet the various requirements of abnormal behavior detection

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Unmanned aerial vehicle abnormal behavior recognition method based on convolutional neural network
  • Unmanned aerial vehicle abnormal behavior recognition method based on convolutional neural network
  • Unmanned aerial vehicle abnormal behavior recognition method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and examples.

[0036] Such as figure 1 As shown, a method of UAV abnormal behavior recognition based on convolutional neural network, including training data and predictive testing. Among them, the training data is the feature extraction of the flight history data of the UAV (GPS accuracy, aircraft X-axis data, aircraft Y-axis data, aircraft Z-axis data, etc.) as input parameters, imported into the constructed CNN model, and trained . After the training is completed, import the new UAV flight data into the model to obtain the judgment result, so as to carry out the prediction test.

[0037] The specific steps of the UAV abnormal behavior identification method are as follows:

[0038] 1. Through the obtained drone flight history data (GPS accuracy, aircraft X-axis d...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an unmanned aerial vehicle abnormal behavior recognition method based on a convolutional neural network. The unmanned aerial vehicle abnormal behavior recognition method comprises the steps: training data and prediction inspection, wherein the training data carries out the feature extraction of flight history data of an unmanned aerial vehicle as an input parameter, importsthe input parameter into a constructed CNN model, and carries out the training; and after the training is completed, new unmanned aerial vehicle flight data is imported into the CNN model to obtain ajudgment result, thereby performing prediction inspection. The unmanned aerial vehicle abnormal behavior recognition method has the advantages that 1, the recognition accuracy is much higher than that of a conventional method; 2, aiming at the conventional illegal problem caused by manual operation of an operator, the illegal problem can be well detected; 3, the system is fully automatic, and thedegree of human intervention is greatly reduced;

Description

technical field [0001] The invention relates to the technical field of drones, in particular to a method for identifying abnormal behavior of drones based on a convolutional neural network. Background technique [0002] UAVs have significant advantages such as strong mobility, light weight, small size, low cost, and high space utilization. , UAVs can respond quickly and undertake the task of transporting emergency supplies such as medical rescue kits, which is of great significance to saving people's lives and property. Or high-altitude remote sensing photography, 24-hour all-weather monitoring, etc. On the other hand, due to the portability of drones, they are not easy to find, etc., and are used by many criminals for illegal purposes. For example: terrorist organizations in Morsu used DJI drones to deliver bombs, causing houses and casualties; Chengdu Shuangliu Airport was once forced to cancel flights because drones were flying nearby, causing serious economic losses, e...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 张学军蒲良唐立
Owner 北航(四川)西部国际创新港科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap